Classification and 3D averaging with missing wedge correction in biological electron tomography

STOPGAP: an open-source package for template matching, subtomogram alignment and classification

Cryo-electron tomography (cryo-ET) enables molecular-resolution 3D imaging of complex biological specimens such as viral particles, cellular sections and, in some cases, whole cells. This enables the structural characterization of molecules in their near-native environments, without the need for purification or separation, thereby preserving biological information such as conformational states and spatial relationships between different molecular species. Subtomogram averaging is an image-processing workflow that allows users to leverage cryo-ET data to identify and localize target molecules, determine high-resolution structures of repeating molecular species and classify different conformational states. Here, STOPGAP, an open-source package for subtomogram averaging that is designed to provide users with fine control over each of these steps, is described. In providing detailed descriptions of the image-processing algorithms that STOPGAP uses, this manuscript is also intended to serve as a technical resource to users as well as for further community-driven software development.

Learning structural heterogeneity from cryo-electron sub-tomograms with tomoDRGN

Cryo-electron tomography (cryo-ET) enables observation of macromolecular complexes in their native, spatially contextualized cellular environment. Cryo-ET processing software to visualize such complexes at nanometer resolution via iterative alignment and averaging are well developed but rely upon assumptions of structural homogeneity among the complexes of interest. Recently developed tools allow for some assessment of structural diversity but have limited capacity to represent highly heterogeneous structures, including those undergoing continuous conformational changes. Here we extend the highly expressive cryoDRGN (Deep Reconstructing Generative Networks) deep learning architecture, originally created for single-particle cryo-electron microscopy analysis, to cryo-ET. Our new tool, tomoDRGN, learns a continuous low-dimensional representation of structural heterogeneity in cryo-ET datasets while also learning to reconstruct heterogeneous structural ensembles supported by the underlying data. Using simulated and experimental data, we describe and benchmark architectural choices within tomoDRGN that are uniquely necessitated and enabled by cryo-ET. We additionally illustrate tomoDRGN's efficacy in analyzing diverse datasets, using it to reveal high-level organization of human immunodeficiency virus (HIV) capsid complexes assembled in virus-like particles and to resolve extensive structural heterogeneity among ribosomes imaged in situ.

DeepETPicker: Fast and accurate 3D particle picking for cryo-electron tomography using weakly supervised deep learning

To solve three-dimensional structures of biological macromolecules in situ, large numbers of particles often need to be picked from cryo-electron tomograms. However, adoption of automated particle-picking methods remains limited because of their technical limitations. To overcome the limitations, we develop DeepETPicker, a deep learning model for fast and accurate picking of particles from cryo-electron tomograms. Training of DeepETPicker requires only weak supervision with low numbers of simplified labels, reducing the burden of manual annotation. The simplified labels combined with the customized and lightweight model architecture of DeepETPicker and accelerated pooling enable substantial performance improvement. When tested on simulated and real tomograms, DeepETPicker outperforms the competing state-of-the-art methods by achieving the highest overall accuracy and speed, which translate into higher authenticity and coordinates accuracy of picked particles and higher resolutions of final reconstruction maps. DeepETPicker is provided in open source with a user-friendly interface to support cryo-electron tomography in situ.

Joint micrograph denoising and protein localization in cryo-electron microscopy

Cryo-electron microscopy (cryo-EM) is an imaging technique that allows the visualization of proteins and macromolecular complexes at near-atomic resolution. The low electron doses used to prevent radiation damage to the biological samples result in images where the power of noise is 100 times stronger than that of the signal. Accurate identification of proteins from these low signal-to-noise ratio (SNR) images is a critical task, as the detected positions serve as inputs for the downstream 3D structure determination process. Current methods either fail to identify all true positives or result in many false positives, especially when analyzing images from smaller-sized proteins that exhibit extremely low contrast, or require manual labeling that can take days to complete. Acknowledging the fact that accurate protein identification is dependent upon the visual interpretability of micrographs, we propose a framework that can perform denoising and detection in a joint manner and enable particle localization under extremely low SNR conditions using self-supervised denoising and particle identification from sparsely annotated data. We validate our approach on three challenging single-particle cryo-EM datasets and projection images from one cryo-electron tomography dataset with extremely low SNR, showing that it outperforms existing state-of-the-art methods used for cryo-EM image analysis by a significant margin. We also evaluate the performance of our algorithm under decreasing SNR conditions and show that our method is more robust to noise than competing methods.

Moment-based metrics for molecules computable from cryogenic electron microscopy images

Single-particle cryogenic electron microscopy (cryo-EM) is an imaging technique capable of recovering the high-resolution three-dimensional (3D) structure of biological macromolecules from many noisy and randomly oriented projection images. One notable approach to 3D reconstruction, known as Kam's method, relies on the moments of the two-dimensional (2D) images. Inspired by Kam's method, we introduce a rotationally invariant metric between two molecular structures, which does not require 3D alignment. Further, we introduce a metric between a stack of projection images and a molecular structure, which is invariant to rotations and reflections and does not require performing 3D reconstruction. Additionally, the latter metric does not assume a uniform distribution of viewing angles. We demonstrate the uses of the new metrics on synthetic and experimental datasets, highlighting their ability to measure structural similarity.

STOPGAP, an open-source package for template matching, subtomogram alignment, and classification

Cryo-electron tomography (cryo-ET) enables molecular-resolution 3D imaging of complex biological specimens such as viral particles, cellular sections, and in some cases, whole cells. This enables the structural characterization of molecules in their near-native environments, without the need for purification or separation, thereby preserving biological information such as conformational states and spatial relationships between different molecular species. Subtomogram averaging is an image processing workflow that allows users to leverage cryo-ET data to identify and localize target molecules, determine high-resolution structures of repeating molecular species, and classifying different conformational states. Here we describe STOPGAP, an open-source package for subtomogram averaging designed to provide users with fine control over each of these steps. In providing detailed descriptions of the image processing algorithms that STOPGAP uses, we intend for this manuscript to also serve as a technical resource to users as well as further community-driven software development.

nextPYP: a comprehensive and scalable platform for characterizing protein variability in situ using single-particle cryo-electron tomography

Single-particle cryo-electron tomography is an emerging technique capable of determining the structure of proteins imaged within the native context of cells at molecular resolution. While high-throughput techniques for sample preparation and tilt-series acquisition are beginning to provide sufficient data to allow structural studies of proteins at physiological concentrations, the complex data analysis pipeline and the demanding storage and computational requirements pose major barriers for the development and broader adoption of this technology. Here, we present a scalable, end-to-end framework for single-particle cryo-electron tomography data analysis from on-the-fly pre-processing of tilt series to high-resolution refinement and classification, which allows efficient analysis and visualization of datasets with hundreds of tilt series and hundreds of thousands of particles. We validate our approach using in vitro and cellular datasets, demonstrating its effectiveness at achieving high-resolution and revealing conformational heterogeneity in situ. The framework is made available through an intuitive and easy-to-use computer application, nextPYP ( http://nextpyp.app ).

Online citizen science with the Zooniverse for analysis of biological volumetric data

Public participation in research, also known as citizen science, is being increasingly adopted for the analysis of biological volumetric data. Researchers working in this domain are applying online citizen science as a scalable distributed data analysis approach, with recent research demonstrating that non-experts can productively contribute to tasks such as the segmentation of organelles in volume electron microscopy data. This, alongside the growing challenge to rapidly process the large amounts of biological volumetric data now routinely produced, means there is increasing interest within the research community to apply online citizen science for the analysis of data in this context. Here, we synthesise core methodological principles and practices for applying citizen science for analysis of biological volumetric data. We collate and share the knowledge and experience of multiple research teams who have applied online citizen science for the analysis of volumetric biological data using the Zooniverse platform ( www.zooniverse.org ). We hope this provides inspiration and practical guidance regarding how contributor effort via online citizen science may be usefully applied in this domain.

MDTOMO method for continuous conformational variability analysis in cryo electron subtomograms based on molecular dynamics simulations

Cryo electron tomography (cryo-ET) allows observing macromolecular complexes in their native environment. The common routine of subtomogram averaging (STA) allows obtaining the three-dimensional (3D) structure of abundant macromolecular complexes, and can be coupled with discrete classification to reveal conformational heterogeneity of the sample. However, the number of complexes extracted from cryo-ET data is usually small, which restricts the discrete-classification results to a small number of enough populated states and, thus, results in a largely incomplete conformational landscape. Alternative approaches are currently being investigated to explore the continuity of the conformational landscapes that in situ cryo-ET studies could provide. In this article, we present MDTOMO, a method for analyzing continuous conformational variability in cryo-ET subtomograms based on Molecular Dynamics (MD) simulations. MDTOMO allows obtaining an atomic-scale model of conformational variability and the corresponding free-energy landscape, from a given set of cryo-ET subtomograms. The article presents the performance of MDTOMO on a synthetic ABC exporter dataset and an in situ SARS-CoV-2 spike dataset. MDTOMO allows analyzing dynamic properties of molecular complexes to understand their biological functions, which could also be useful for structure-based drug discovery.

Computational Methods Toward Unbiased Pattern Mining and Structure Determination in Cryo-Electron Tomography Data

Cryo-electron tomography can uniquely probe the native cellular environment for macromolecular structures. Tomograms feature complex data with densities of diverse, densely crowded macromolecular complexes, low signal-to-noise, and artifacts such as the missing wedge effect. Post-processing of this data generally involves isolating regions or particles of interest from tomograms, organizing them into related groups, and rendering final structures through subtomogram averaging. Template-matching and reference-based structure determination are popular analysis methods but are vulnerable to biases and can often require significant user input. Most importantly, these approaches cannot identify novel complexes that reside within the imaged cellular environment. To reliably extract and resolve structures of interest, efficient and unbiased approaches are therefore of great value. This review highlights notable computational software and discusses how they contribute to making automated structural pattern discovery a possibility. Perspectives emphasizing the importance of features for user-friendliness and accessibility are also presented.

Methods to Evaluate Changes in Mitochondrial Structure and Function in Cancer

Mitochondria are regulators of key cellular processes, including energy production and redox homeostasis. Mitochondrial dysfunction is associated with various human diseases, including cancer. Importantly, both structural and functional changes can alter mitochondrial function. Morphologic and quantifiable changes in mitochondria can affect their function and contribute to disease. Structural mitochondrial changes include alterations in cristae morphology, mitochondrial DNA integrity and quantity, and dynamics, such as fission and fusion. Functional parameters related to mitochondrial biology include the production of reactive oxygen species, bioenergetic capacity, calcium retention, and membrane potential. Although these parameters can occur independently of one another, changes in mitochondrial structure and function are often interrelated. Thus, evaluating changes in both mitochondrial structure and function is crucial to understanding the molecular events involved in disease onset and progression. This review focuses on the relationship between alterations in mitochondrial structure and function and cancer, with a particular emphasis on gynecologic malignancies. Selecting methods with tractable parameters may be critical to identifying and targeting mitochondria-related therapeutic options. Methods to measure changes in mitochondrial structure and function, with the associated benefits and limitations, are summarized.

High-throughput cryo-ET structural pattern mining by unsupervised deep iterative subtomogram clustering

Cryoelectron tomography directly visualizes heterogeneous macromolecular structures in their native and complex cellular environments. However, existing computer-assisted structure sorting approaches are low throughput or inherently limited due to their dependency on available templates and manual labels. Here, we introduce a high-throughput template-and-label-free deep learning approach, Deep Iterative Subtomogram Clustering Approach (DISCA), that automatically detects subsets of homogeneous structures by learning and modeling 3D structural features and their distributions. Evaluation on five experimental cryo-ET datasets shows that an unsupervised deep learning based method can detect diverse structures with a wide range of molecular sizes. This unsupervised detection paves the way for systematic unbiased recognition of macromolecular complexes in situ.

Real-time tilt undersampling optimization during electron tomography of beam sensitive samples using golden ratio scanning and RECAST3D

Electron tomography is a widely used technique for 3D structural analysis of nanomaterials, but it can cause damage to samples due to high electron doses and long exposure times. To minimize such damage, researchers often reduce beam exposure by acquiring fewer projections through tilt undersampling. However, this approach can also introduce reconstruction artifacts due to insufficient sampling. Therefore, it is important to determine the optimal number of projections that minimizes both beam exposure and undersampling artifacts for accurate reconstructions of beam-sensitive samples. Current methods for determining this optimal number of projections involve acquiring and post-processing multiple reconstructions with different numbers of projections, which can be time-consuming and requires multiple samples due to sample damage. To improve this process, we propose a protocol that combines golden ratio scanning and quasi-3D reconstruction to estimate the optimal number of projections in real-time during a single acquisition. This protocol was validated using simulated and realistic nanoparticles, and was successfully applied to reconstruct two beam-sensitive metal-organic framework complexes.

Algorithm for Modern Electron Microscopic Examination of the Golgi Complex

The Golgi complex (GC) is an essential organelle of the eukaryotic exocytic pathway. It has a very complexed structure and thus localization of its resident proteins is not trivial. Fast development of microscopic methods generates a huge difficulty for Golgi researchers to select the best protocol to use. Modern methods of light microscopy, such as super-resolution light microscopy (SRLM) and electron microscopy (EM), open new possibilities in analysis of various biological structures at organelle, cell, and organ levels. Nowadays, new generation of EM methods became available for the study of the GC; these include three-dimensional EM (3DEM), correlative light-EM (CLEM), immune EM, and new estimators within stereology that allow realization of maximal goal of any morphological study, namely, to achieve a three-dimensional model of the sample with optimal level of resolution and quantitative determination of its chemical composition. Methods of 3DEM have partially overlapping capabilities. This requires a careful comparison of these methods, identification of their strengths and weaknesses, and formulation of recommendations for their application to cell or tissue samples. Here, we present an overview of 3DEM methods for the study of the GC and some basics for how the images are formed and how the image quality can be improved.

Studying membrane modulation mechanisms by electron cryo-tomography

Membrane modulation is a key part of cellular life. Critical to processes like energy production, cell division, trafficking, migration and even pathogen entry, defects in membrane modulation are often associated with diseases. Studying the molecular mechanisms of membrane modulation is challenging due to the highly dynamic nature of the oligomeric assemblies involved, which adopt multiple conformations depending on the precise event they are participating in. With the development of electron cryo-tomography and subtomogram averaging, many of these challenges are being resolved as it is now possible to observe complex macromolecular assemblies inside a cell at nanometre to sub-nanometre resolutions. Here, we review the different ways electron cryo-tomography is being used to help uncover the molecular mechanisms used by cells to shape their membranes.

MEPSi: A tool for simulating tomograms of membrane-embedded proteins

The throughput and fidelity of cryogenic cellular electron tomography (cryo-ET) is constantly increasing through advances in cryogenic electron microscope hardware, direct electron detection devices, and powerful image processing algorithms. However, the need for careful optimization of sample preparations and for access to expensive, high-end equipment, make cryo-ET a costly and time-consuming technique. Generally, only after the last step of the cryo-ET workflow, when reconstructed tomograms are available, it becomes clear whether the chosen imaging parameters were suitable for a specific type of sample in order to answer a specific biological question. Tools for a-priory assessment of the feasibility of samples to answer biological questions and how to optimize imaging parameters to do so would be a major advantage. Here we describe MEPSi (Membrane Embedded Protein Simulator), a simulation tool aimed at rapid and convenient evaluation and optimization of cryo-ET data acquisition parameters for studies of transmembrane proteins in their native environment. We demonstrate the utility of MEPSi by showing how to detangle the influence of different data collection parameters and different orientations in respect to tilt axis and electron beam for two examples: (1) simulated plasma membranes with embedded single-pass transmembrane αIIbβ3 integrin receptors and (2) simulated virus membranes with embedded SARS-CoV-2 spike proteins.

Cryo-electron tomography related radiation-damage parameters for individual-molecule 3D structure determination

To understand the dynamic structure-function relationship of soft- and biomolecules, the determination of the three-dimensional (3D) structure of each individual molecule (nonaveraged structure) in its native state is sought-after. Cryo-electron tomography (cryo-ET) is a unique tool for imaging an individual object from a series of tilted views. However, due to radiation damage from the incident electron beam, the tolerable electron dose limits image contrast and the signal-to-noise ratio (SNR) of the data, preventing the 3D structure determination of individual molecules, especially at high-resolution. Although recently developed technologies and techniques, such as the direct electron detector, phase plate, and computational algorithms, can partially improve image contrast/SNR at the same electron dose, the high-resolution structure, such as tertiary structure of individual molecules, has not yet been resolved. Here, we review the cryo-electron microscopy (cryo-EM) and cryo-ET experimental parameters to discuss how these parameters affect the extent of radiation damage. This discussion can guide us in optimizing the experimental strategy to increase the imaging dose or improve image SNR without increasing the radiation damage. With a higher dose, a higher image contrast/SNR can be achieved, which is crucial for individual-molecule 3D structure. With 3D structures determined from an ensemble of individual molecules in different conformations, the molecular mechanism through their biochemical reactions, such as self-folding or synthesis, can be elucidated in a straightforward manner.

High-resolution structure determination using high-throughput electron cryo-tomography

In this article, it is shown that high-throughput strategies for tomographic data acquisition combined with unsupervised techniques for image analysis provide the foundation for closing the resolution gap between the high-resolution strategies used to study molecular assemblies reconstituted in vitro and techniques for in situ structure determination.

Tomographic reconstruction of frozen-hydrated specimens followed by extraction and averaging of sub-tomograms has successfully been used to determine the structure of macromolecules in their native environment at resolutions that are high enough to reveal molecular level interactions. The low throughput characteristic of tomographic data acquisition combined with the complex data-analysis pipeline that is required to obtain high-resolution maps, however, has limited the applicability of this technique to favorable samples or to resolutions that are too low to provide useful mechanistic information. Recently, beam image-shift electron cryo-tomography (BISECT), a strategy to significantly accelerate the acquisition of tilt series without sacrificing image quality, was introduced. The ability to produce thousands of high-quality tilt series during a single microscope session, however, introduces significant bottlenecks in the downstream data analysis, which has so far relied on specialized pipelines. Here, recent advances in accurate estimation of the contrast transfer function and self-tuning exposure-weighting routines that contribute to improving the resolution and streamlining the structure-determination process using sub-volume averaging are reviewed. Ultimately, the combination of automated data-driven techniques for image analysis together with high-throughput strategies for tilt-series acquisition will pave the way for tomography to become the technique of choice for in situ structure determination.

Cryo-shift: reducing domain shift in cryo-electron subtomograms with unsupervised domain adaptation and randomization

MOTIVATION

Cryo-Electron Tomography (cryo-ET) is a 3D imaging technology that enables the visualization of subcellular structures in situ at near-atomic resolution. Cellular cryo-ET images help in resolving the structures of macromolecules and determining their spatial relationship in a single cell, which has broad significance in cell and structural biology. Subtomogram classification and recognition constitute a primary step in the systematic recovery of these macromolecular structures. Supervised deep learning methods have been proven to be highly accurate and efficient for subtomogram classification, but suffer from limited applicability due to scarcity of annotated data. While generating simulated data for training supervised models is a potential solution, a sizeable difference in the image intensity distribution in generated data as compared with real experimental data will cause the trained models to perform poorly in predicting classes on real subtomograms.

RESULTS

In this work, we present Cryo-Shift, a fully unsupervised domain adaptation and randomization framework for deep learning-based cross-domain subtomogram classification. We use unsupervised multi-adversarial domain adaption to reduce the domain shift between features of simulated and experimental data. We develop a network-driven domain randomization procedure with 'warp' modules to alter the simulated data and help the classifier generalize better on experimental data. We do not use any labeled experimental data to train our model, whereas some of the existing alternative approaches require labeled experimental samples for cross-domain classification. Nevertheless, Cryo-Shift outperforms the existing alternative approaches in cross-domain subtomogram classification in extensive evaluation studies demonstrated herein using both simulated and experimental data.

AVAILABILITYAND IMPLEMENTATION

https://github.com/xulabs/aitom.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

CryoETGAN: Cryo-Electron Tomography Image Synthesis via Unpaired Image Translation

Cryo-electron tomography (Cryo-ET) has been regarded as a revolution in structural biology and can reveal molecular sociology. Its unprecedented quality enables it to visualize cellular organelles and macromolecular complexes at nanometer resolution with native conformations. Motivated by developments in nanotechnology and machine learning, establishing machine learning approaches such as classification, detection and averaging for Cryo-ET image analysis has inspired broad interest. Yet, deep learning-based methods for biomedical imaging typically require large labeled datasets for good results, which can be a great challenge due to the expense of obtaining and labeling training data. To deal with this problem, we propose a generative model to simulate Cryo-ET images efficiently and reliably: CryoETGAN. This cycle-consistent and Wasserstein generative adversarial network (GAN) is able to generate images with an appearance similar to the original experimental data. Quantitative and visual grading results on generated images are provided to show that the results of our proposed method achieve better performance compared to the previous state-of-the-art simulation methods. Moreover, CryoETGAN is stable to train and capable of generating plausibly diverse image samples.

A Bayesian approach to single-particle electron cryo-tomography in RELION-4.0

We present a new approach for macromolecular structure determination from multiple particles in electron cryo-tomography (cryo-ET) data sets. Whereas existing subtomogram averaging approaches are based on 3D data models, we propose to optimise a regularised likelihood target that approximates a function of the 2D experimental images. In addition, analogous to Bayesian polishing and contrast transfer function (CTF) refinement in single-particle analysis, we describe the approaches that exploit the increased signal-to-noise ratio in the averaged structure to optimise tilt-series alignments, beam-induced motions of the particles throughout the tilt-series acquisition, defoci of the individual particles, as well as higher-order optical aberrations of the microscope. Implementation of our approaches in the open-source software package RELION aims to facilitate their general use, particularly for those researchers who are already familiar with its single-particle analysis tools. We illustrate for three applications that our approaches allow structure determination from cryo-ET data to resolutions sufficient for de novo atomic modelling.

Macromolecules Structural Classification With a 3D Dilated Dense Network in Cryo-Electron Tomography

Cryo-electron tomography, combined with subtomogram averaging (STA), can reveal three-dimensional (3D) macromolecule structures in the near-native state from cells and other biological samples. In STA, to get a high-resolution 3D view of macromolecule structures, diverse macromolecules captured by the cellular tomograms need to be accurately classified. However, due to the poor signal-to-noise-ratio (SNR) and severe ray artifacts in the tomogram, it remains a major challenge to classify macromolecules with high accuracy. In this paper, we propose a new convolutional neural network, named 3D-Dilated-DenseNet, to improve the performance of macromolecule classification. In 3D-Dilated-DenseNet, there are two key strategies to guarantee macromolecule classification accuracy: 1) Using dense connections to enhance feature map utilization (corresponding to the baseline 3D-C-DenseNet); 2) Adopting dilated convolution to enrich multi-level information in feature maps. We tested 3D-Dilated-DenseNet and 3D-C-DenseNet both on synthetic data and experimental data. The results show that, on synthetic data, compared with the state-of-the-art method in the SHREC contest (SHREC-CNN), both 3D-C-DenseNet and 3D-Dilated-DenseNet outperform SHREC-CNN. In particular, 3D-Dilated-DenseNet improves 0.393 of F1 metric on tiny-size macromolecules and 0.213 on small-size macromolecules. On experimental data, compared with 3D-C-DenseNet, 3D-Dilated-DenseNet can increase classification performance by 2.1 percent.

Recent Advances and Prospects in Colloidal Nanomaterials

Colloidal nanomaterials of metals, metal oxides, and metal chalcogenides have attracted great attention in the past decade owing to their potential applications in optoelectronics, catalysis, and energy conversion. Introduction of various synthetic routes has resulted in diverse colloidal nanostructured materials with well-controlled size, shape, and composition, enabling the systematic study of their intriguing physicochemical, optoelectronic, and chemical properties. Furthermore, developments in the instrumentation have offered valuable insights into the nucleation and growth mechanism of these nanomaterials, which are crucial in designing prospective materials with desired properties. In this perspective, recent advances in the colloidal synthesis and mechanism studies of nanomaterials of metal chalcogenides, metals, and metal oxides are discussed. In addition, challenges in the characterization and future direction of the colloidal nanomaterials are provided.

Cryo-electron tomography provides topological insights into mutant huntingtin exon 1 and polyQ aggregates

Huntington disease (HD) is a neurodegenerative trinucleotide repeat disorder caused by an expanded poly-glutamine (polyQ) tract in the mutant huntingtin (mHTT) protein. The formation and topology of filamentous mHTT inclusions in the brain (hallmarks of HD implicated in neurotoxicity) remain elusive. Using cryo-electron tomography and subtomogram averaging, here we show that mHTT exon 1 and polyQ-only aggregates in vitro are structurally heterogenous and filamentous, similar to prior observations with other methods. Yet, we find filaments in both types of aggregates under ~2 nm in width, thinner than previously reported, and regions forming large sheets. In addition, our data show a prevalent subpopulation of filaments exhibiting a lumpy slab morphology in both aggregates, supportive of the polyQ core model. This provides a basis for future cryoET studies of various aggregated mHTT and polyQ constructs to improve their structure-based modeling as well as their identification in cells without fusion tags.

Locating macromolecular assemblies in cells by 2D template matching with cisTEM

For a more complete understanding of molecular mechanisms, it is important to study macromolecules and their assemblies in the broader context of the cell. This context can be visualized at nanometer resolution in three dimensions (3D) using electron cryo-tomography, which requires tilt series to be recorded and computationally aligned, currently limiting throughput. Additionally, the high-resolution signal preserved in the raw tomograms is currently limited by a number of technical difficulties, leading to an increased false-positive detection rate when using 3D template matching to find molecular complexes in tomograms. We have recently described a 2D template matching approach that addresses these issues by including high-resolution signal preserved in single-tilt images. A current limitation of this approach is the high computational cost that limits throughput. We describe here a GPU-accelerated implementation of 2D template matching in the image processing software cisTEM that allows for easy scaling and improves the accessibility of this approach. We apply 2D template matching to identify ribosomes in images of frozen-hydrated Mycoplasma pneumoniae cells with high precision and sensitivity, demonstrating that this is a versatile tool for in situ visual proteomics and in situ structure determination. We benchmark the results with 3D template matching of tomograms acquired on identical sample locations and identify strengths and weaknesses of both techniques, which offer complementary information about target localization and identity.

Current data processing strategies for cryo-electron tomography and subtomogram averaging

Cryo-electron tomography (cryo-ET) can be used to reconstruct three-dimensional (3D) volumes, or tomograms, from a series of tilted two-dimensional images of biological objects in their near-native states in situ or in vitro. 3D subvolumes, or subtomograms, containing particles of interest can be extracted from tomograms, aligned, and averaged in a process called subtomogram averaging (STA). STA overcomes the low signal to noise ratio within the individual subtomograms to generate structures of the particle(s) of interest. In recent years, cryo-ET with STA has increasingly been capable of reaching subnanometer resolution due to improvements in microscope hardware and data processing strategies. There has also been an increase in the number and quality of software packages available to process cryo-ET data with STA. In this review, we describe and assess the data processing strategies available for cryo-ET data and highlight the recent software developments which have enabled the extraction of high-resolution information from cryo-ET datasets.

Immature HIV-1 assembles from Gag dimers leaving partial hexamers at lattice edges as potential substrates for proteolytic maturation

HIV-1 particle assembly is driven by the viral Gag protein, which oligomerizes into a hexameric array on the inner surface of the viral envelope, forming a truncated spherical lattice containing large and small gaps. Gag is then cut by the viral protease, disassembles, and rearranges to form the mature, infectious virus. Here, we present structures and molecular dynamics simulations of the edges of the immature Gag lattice. Our analysis shows that Gag dimers are the basic assembly unit of the HIV-1 particle, lattice edges are partial hexamers, and partial hexamers are prone to structural changes allowing protease to cut Gag. These findings provide insights into assembly of the immature virus, its structure, and how it disassembles during maturation.

The CA (capsid) domain of immature HIV-1 Gag and the adjacent spacer peptide 1 (SP1) play a key role in viral assembly by forming a lattice of CA hexamers, which adapts to viral envelope curvature by incorporating small lattice defects and a large gap at the site of budding. This lattice is stabilized by intrahexameric and interhexameric CA-CA interactions, which are important in regulating viral assembly and maturation. We applied subtomogram averaging and classification to determine the oligomerization state of CA at lattice edges and found that CA forms partial hexamers. These structures reveal the network of interactions formed by CA-SP1 at the lattice edge. We also performed atomistic molecular dynamics simulations of CA-CA interactions stabilizing the immature lattice and partial CA-SP1 helical bundles. Free energy calculations reveal increased propensity for helix-to-coil transitions in partial hexamers compared to complete six-helix bundles. Taken together, these results suggest that the CA dimer is the basic unit of lattice assembly, partial hexamers exist at lattice edges, these are in a helix-coil dynamic equilibrium, and partial helical bundles are more likely to unfold, representing potential sites for HIV-1 maturation initiation.

Few shot domain adaptation for in situ macromolecule structural classification in cryoelectron tomograms

MOTIVATION

Cryoelectron tomography (cryo-ET) visualizes structure and spatial organization of macromolecules and their interactions with other subcellular components inside single cells in the close-to-native state at submolecular resolution. Such information is critical for the accurate understanding of cellular processes. However, subtomogram classification remains one of the major challenges for the systematic recognition and recovery of the macromolecule structures in cryo-ET because of imaging limits and data quantity. Recently, deep learning has significantly improved the throughput and accuracy of large-scale subtomogram classification. However, often it is difficult to get enough high-quality annotated subtomogram data for supervised training due to the enormous expense of labeling. To tackle this problem, it is beneficial to utilize another already annotated dataset to assist the training process. However, due to the discrepancy of image intensity distribution between source domain and target domain, the model trained on subtomograms in source domain may perform poorly in predicting subtomogram classes in the target domain.

RESULTS

In this article, we adapt a few shot domain adaptation method for deep learning-based cross-domain subtomogram classification. The essential idea of our method consists of two parts: (i) take full advantage of the distribution of plentiful unlabeled target domain data, and (ii) exploit the correlation between the whole source domain dataset and few labeled target domain data. Experiments conducted on simulated and real datasets show that our method achieves significant improvement on cross domain subtomogram classification compared with baseline methods.

AVAILABILITY AND IMPLEMENTATION

Software is available online https://github.com/xulabs/aitom.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Beam image-shift accelerated data acquisition for near-atomic resolution single-particle cryo-electron tomography

Tomographic reconstruction of cryopreserved specimens imaged in an electron microscope followed by extraction and averaging of sub-volumes has been successfully used to derive atomic models of macromolecules in their biological environment. Eliminating biochemical isolation steps required by other techniques, this method opens up the cell to in-situ structural studies. However, the need to compensate for errors in targeting introduced during mechanical navigation of the specimen significantly slows down tomographic data collection thus limiting its practical value. Here, we introduce protocols for tilt-series acquisition and processing that accelerate data collection speed by up to an order of magnitude and improve map resolution compared to existing approaches. We achieve this by using beam-image shift to multiply the number of areas imaged at each stage position, by integrating geometrical constraints during imaging to achieve high precision targeting, and by performing per-tilt astigmatic CTF estimation and data-driven exposure weighting to improve final map resolution. We validated our beam image-shift electron cryo-tomography (BISECT) approach by determining the structure of a low molecular weight target (~300 kDa) at 3.6 Å resolution where density for individual side chains is clearly resolved.

Tomographic reconstructions of cryopreserved specimens enable in-situ structural studies. Here, the authors present the beam image-shift electron cryo-tomography (BISECT) approach that accelerates data collection speed and improves the map resolution compared to earlier approaches and present the in vitro structure of a 300 kDa protein complex that was solved at 3.6 Å resolution as a test case.

The promise and the challenges of cryo-electron tomography

Structural biologists have traditionally approached cellular complexity in a reductionist manner in which the cellular molecular components are fractionated and purified before being studied individually. This 'divide and conquer' approach has been highly successful. However, awareness has grown in recent years that biological functions can rarely be attributed to individual macromolecules. Most cellular functions arise from their concerted action, and there is thus a need for methods enabling structural studies performed in situ, ideally in unperturbed cellular environments. Cryo-electron tomography (Cryo-ET) combines the power of 3D molecular-level imaging with the best structural preservation that is physically possible to achieve. Thus, it has a unique potential to reveal the supramolecular architecture or 'molecular sociology' of cells and to discover the unexpected. Here, we review state-of-the-art Cryo-ET workflows, provide examples of biological applications, and discuss what is needed to realize the full potential of Cryo-ET.

LoTToR: An Algorithm for Missing-Wedge Correction of the Low-Tilt Tomographic 3D Reconstruction of a Single-Molecule Structure

A single-molecule three-dimensional (3D) structure is essential for understanding the thermal vibrations and dynamics as well as the conformational changes during the chemical reaction of macromolecules. Individual-particle electron tomography (IPET) is an approach for obtaining a snap-shot 3D structure of an individual macromolecule particle by aligning the tilt series of electron tomographic (ET) images of a targeted particle through a focused iterative 3D reconstruction method. The method can reduce the influence on the 3D reconstruction from large-scale image distortion and deformation. Due to the mechanical tilt limitation, 3D reconstruction often contains missing-wedge artifacts, presented as elongation and an anisotropic resolution. Here, we report a post-processing method to correct the missing-wedge artifact. This low-tilt tomographic reconstruction (LoTToR) method contains a model-free iteration process under a set of constraints in real and reciprocal spaces. A proof of concept is conducted by using the LoTToR on a phantom, i.e., a simulated 3D reconstruction from a low-tilt series of images, including that within a tilt range of ±15°. The method is validated by using both negative-staining (NS) and cryo-electron tomography (cryo-ET) experimental data. A significantly reduced missing-wedge artifact verifies the capability of LoTToR, suggesting a new tool to support the future study of macromolecular dynamics, fluctuation and chemical activity from the viewpoint of single-molecule 3D structure determination.

Gum-Net: Unsupervised Geometric Matching for Fast and Accurate 3D Subtomogram Image Alignment and Averaging

We propose a Geometric unsupervised matching Network (Gum-Net) for finding the geometric correspondence between two images with application to 3D subtomogram alignment and averaging. Subtomogram alignment is the most important task in cryo-electron tomography (cryo-ET), a revolutionary 3D imaging technique for visualizing the molecular organization of unperturbed cellular landscapes in single cells. However, subtomogram alignment and averaging are very challenging due to severe imaging limits such as noise and missing wedge effects. We introduce an end-to-end trainable architecture with three novel modules specifically designed for preserving feature spatial information and propagating feature matching information. The training is performed in a fully unsupervised fashion to optimize a matching metric. No ground truth transformation information nor category-level or instance-level matching supervision information is needed. After systematic assessments on six real and nine simulated datasets, we demonstrate that Gum-Net reduced the alignment error by 40 to 50% and improved the averaging resolution by 10%. Gum-Net also achieved 70 to 110 times speedup in practice with GPU acceleration compared to state-of-the-art subtomogram alignment methods. Our work is the first 3D unsupervised geometric matching method for images of strong transformation variation and high noise level. The training code, trained model, and datasets are available in our open-source software AITom.

LamNI - an instrument for X-ray scanning microscopy in laminography geometry

Across all branches of science, medicine and engineering, high-resolution microscopy is required to understand functionality. Although optical methods have been developed to `defeat' the diffraction limit and produce 3D images, and electrons have proven ever more useful in creating pictures of small objects or thin sections, so far there is no substitute for X-ray microscopy in providing multiscale 3D images of objects with a single instrument and minimal labeling and preparation. A powerful technique proven to continuously access length scales from 10 nm to 10 µm is ptychographic X-ray computed tomography, which, on account of the orthogonality of the tomographic rotation axis to the illuminating beam, still has the limitation of necessitating pillar-shaped samples of small (ca 10 µm) diameter. Large-area planar samples are common in science and engineering, and it is therefore highly desirable to create an X-ray microscope that can examine such samples without the extraction of pillars. Computed laminography, where the axis of rotation is not perpendicular to the illumination direction, solves this problem. This entailed the development of a new instrument, LamNI, dedicated to high-resolution 3D scanning X-ray microscopy via hard X-ray ptychographic laminography. Scanning precision is achieved by a dedicated interferometry scheme and the instrument covers a scan range of 12 mm × 12 mm with a position stability of 2 nm and positioning errors below 5 nm. A new feature of LamNI is a pair of counter-rotating stages carrying the sample and interferometric mirrors, respectively.

Critical differences in 3D atomic structure of individual ligand-protected nanocrystals in solution

Precise three-dimensional (3D) atomic structure determination of individual nanocrystals is a prerequisite for understanding and predicting their physical properties. Nanocrystals from the same synthesis batch display what are often presumed to be small but possibly important differences in size, lattice distortions, and defects, which can only be understood by structural characterization with high spatial 3D resolution. We solved the structures of individual colloidal platinum nanocrystals by developing atomic-resolution 3D liquid-cell electron microscopy to reveal critical intrinsic heterogeneity of ligand-protected platinum nanocrystals in solution, including structural degeneracies, lattice parameter deviations, internal defects, and strain. These differences in structure lead to substantial contributions to free energies, consequential enough that they must be considered in any discussion of fundamental nanocrystal properties or applications.

Fine-grained alignment of cryo-electron subtomograms based on MPI parallel optimization

BACKGROUND

Cryo-electron tomography (Cryo-ET) is an imaging technique used to generate three-dimensional structures of cellular macromolecule complexes in their native environment. Due to developing cryo-electron microscopy technology, the image quality of three-dimensional reconstruction of cryo-electron tomography has greatly improved. However, cryo-ET images are characterized by low resolution, partial data loss and low signal-to-noise ratio (SNR). In order to tackle these challenges and improve resolution, a large number of subtomograms containing the same structure needs to be aligned and averaged. Existing methods for refining and aligning subtomograms are still highly time-consuming, requiring many computationally intensive processing steps (i.e. the rotations and translations of subtomograms in three-dimensional space).

RESULTS

In this article, we propose a Stochastic Average Gradient (SAG) fine-grained alignment method for optimizing the sum of dissimilarity measure in real space. We introduce a Message Passing Interface (MPI) parallel programming model in order to explore further speedup.

CONCLUSIONS

We compare our stochastic average gradient fine-grained alignment algorithm with two baseline methods, high-precision alignment and fast alignment. Our SAG fine-grained alignment algorithm is much faster than the two baseline methods. Results on simulated data of GroEL from the Protein Data Bank (PDB ID:1KP8) showed that our parallel SAG-based fine-grained alignment method could achieve close-to-optimal rigid transformations with higher precision than both high-precision alignment and fast alignment at a low SNR (SNR=0.003) with tilt angle range ±60∘ or ±40∘. For the experimental subtomograms data structures of GroEL and GroEL/GroES complexes, our parallel SAG-based fine-grained alignment can achieve higher precision and fewer iterations to converge than the two baseline methods.

An integration of fast alignment and maximum-likelihood methods for electron subtomogram averaging and classification

Motivation

Cellular Electron CryoTomography (CECT) is an emerging 3D imaging technique that visualizes subcellular organization of single cells at sub-molecular resolution and in near-native state. CECT captures large numbers of macromolecular complexes of highly diverse structures and abundances. However, the structural complexity and imaging limits complicate the systematic de novo structural recovery and recognition of these macromolecular complexes. Efficient and accurate reference-free subtomogram averaging and classification represent the most critical tasks for such analysis. Existing subtomogram alignment based methods are prone to the missing wedge effects and low signal-to-noise ratio (SNR). Moreover, existing maximum-likelihood based methods rely on integration operations, which are in principle computationally infeasible for accurate calculation.

Results

Built on existing works, we propose an integrated method, Fast Alignment Maximum Likelihood method (FAML), which uses fast subtomogram alignment to sample sub-optimal rigid transformations. The transformations are then used to approximate integrals for maximum-likelihood update of subtomogram averages through expectation–maximization algorithm. Our tests on simulated and experimental subtomograms showed that, compared to our previously developed fast alignment method (FA), FAML is significantly more robust to noise and missing wedge effects with moderate increases of computation cost. Besides, FAML performs well with significantly fewer input subtomograms when the FA method fails. Therefore, FAML can serve as a key component for improved construction of initial structural models from macromolecules captured by CECT.

Availability and implementation

http://www.cs.cmu.edu/mxu1

Adversarial domain adaptation for cross data source macromolecule in situ structural classification in cellular electron cryo-tomograms

MOTIVATION

Since 2017, an increasing amount of attention has been paid to the supervised deep learning-based macromolecule in situ structural classification (i.e. subtomogram classification) in cellular electron cryo-tomography (CECT) due to the substantially higher scalability of deep learning. However, the success of such supervised approach relies heavily on the availability of large amounts of labeled training data. For CECT, creating valid training data from the same data source as prediction data is usually laborious and computationally intensive. It would be beneficial to have training data from a separate data source where the annotation is readily available or can be performed in a high-throughput fashion. However, the cross data source prediction is often biased due to the different image intensity distributions (a.k.a. domain shift).

RESULTS

We adapt a deep learning-based adversarial domain adaptation (3D-ADA) method to timely address the domain shift problem in CECT data analysis. 3D-ADA first uses a source domain feature extractor to extract discriminative features from the training data as the input to a classifier. Then it adversarially trains a target domain feature extractor to reduce the distribution differences of the extracted features between training and prediction data. As a result, the same classifier can be directly applied to the prediction data. We tested 3D-ADA on both experimental and realistically simulated subtomogram datasets under different imaging conditions. 3D-ADA stably improved the cross data source prediction, as well as outperformed two popular domain adaptation methods. Furthermore, we demonstrate that 3D-ADA can improve cross data source recovery of novel macromolecular structures.

AVAILABILITY AND IMPLEMENTATION

https://github.com/xulabs/projects.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Subtomogram averaging from cryo-electron tomograms

Cryo-electron tomography (cryo-ET) allows three-dimensional (3D) visualization of frozen-hydrated biological samples, such as protein complexes and cell organelles, in near-native environments at nanometer scale. Protein complexes that are present in multiple copies in a set of tomograms can be extracted, mutually aligned, and averaged to yield a signal-enhanced 3D structure up to sub-nanometer or even near-atomic resolution. This technique, called subtomogram averaging (StA), is powered by improvements in EM hardware and image processing software. Importantly, StA provides unique biological insights into the structure and function of cellular machinery in close-to-native contexts. In this chapter, we describe the principles and key steps of StA. We briefly cover sample preparation and data collection with an emphasis on image processing procedures related to tomographic reconstruction, subtomogram alignment, averaging, and classification. We conclude by summarizing current limitations and future directions of this technique with a focus on high-resolution StA.

Frontiers in Cryo Electron Microscopy of Complex Macromolecular Assemblies

In recent years, cryo electron microscopy (cryo-EM) technology has been transformed with the development of better instrumentation, direct electron detectors, improved methods for specimen preparation, and improved software for data analysis. Analyses using single-particle cryo-EM methods have enabled determination of structures of proteins with sizes smaller than 100 kDa and resolutions of ∼2 Å in some cases. The use of electron tomography combined with subvolume averaging is beginning to allow the visualization of macromolecular complexes in their native environment in unprecedented detail. As a result of these advances, solutions to many intractable challenges in structural and cell biology, such as analysis of highly dynamic soluble and membrane-embedded protein complexes or partially ordered protein aggregates, are now within reach. Recent reports of structural studies of G protein-coupled receptors, spliceosomes, and fibrillar specimens illustrate the progress that has been made using cryo-EM methods, and are the main focus of this review.

De Novo Structural Pattern Mining in Cellular Electron Cryotomograms

Electron cryotomography enables 3D visualization of cells in a near-native state at molecular resolution. The produced cellular tomograms contain detailed information about a plethora of macromolecular complexes, their structures, abundances, and specific spatial locations in the cell. However, extracting this information in a systematic way is very challenging, and current methods usually rely on individual templates of known structures. Here, we propose a framework called "Multi-Pattern Pursuit" for de novo discovery of different complexes from highly heterogeneous sets of particles extracted from entire cellular tomograms without using information of known structures. These initially detected structures can then serve as input for more targeted refinement efforts. Our tests on simulated and experimental tomograms show that our automated method is a promising tool for supporting large-scale template-free visual proteomics analysis.

Improved deep learning-based macromolecules structure classification from electron cryo-tomograms

Cellular processes are governed by macromolecular complexes inside the cell. Study of the native structures of macromolecular complexes has been extremely difficult due to lack of data. With recent breakthroughs in Cellular Electron Cryo-Tomography (CECT) 3D imaging technology, it is now possible for researchers to gain accesses to fully study and understand the macro-molecular structures single cells. However, systematic recovery of macromolecular structures from CECT is very difficult due to high degree of structural complexity and practical imaging limitations. Specifically, we proposed a deep learning-based image classification approach for large-scale systematic macromolecular structure separation from CECT data. However, our previous work was only a very initial step toward exploration of the full potential of deep learning-based macromolecule separation. In this paper, we focus on improving classification performance by proposing three newly designed individual CNN models: an extended version of (Deep Small Receptive Field) DSRF3D, donated as DSRF3D-v2, a 3D residual block-based neural network, named as RB3D, and a convolutional 3D (C3D)-based model, CB3D. We compare them with our previously developed model (DSRF3D) on 12 datasets with different SNRs and tilt angle ranges. The experiments show that our new models achieved significantly higher classification accuracies. The accuracies are not only higher than 0.9 on normal datasets, but also demonstrate potentials to operate on datasets with high levels of noises and missing wedge effects presented.

emClarity: software for high-resolution cryo-electron tomography and subtomogram averaging

Macromolecular complexes are intrinsically flexible and often challenging to purify for structure determination by single particle cryoEM. Such complexes may be studied using cryo-electron tomography combined with sub-tomogram alignment and classification, which in exceptional cases reaches sub-nanometer resolution, yielding insight into structure-function relationships. Extending this approach to specimens that exhibit conformational or compositional heterogeneity, and that may be present at low abundance, remains challenging. To address this challenge, we developed emClarity (https://github.com/bHimes/emClarity/wiki), a GPU-accelerated image processing package, which features an iterative tomographic tilt-series refinement algorithm using sub-tomograms as fiducial markers and a 3D-samping function compensated, multi-scale Principle Component Analysis classification method. We demonstrate substantial improvements in the resolution of maps and in the separation of different functional states of macromolecular complexes, compared to those generated using current state-of-the-art software.

DEEP LEARNING BASED SUPERVISED SEMANTIC SEGMENTATION OF ELECTRON CRYO-SUBTOMOGRAMS

Cellular Electron Cryo-Tomography (CECT) is a powerful imaging technique for the 3D visualization of cellular structure and organization at submolecular resolution. It enables analyzing the native structures of macromolecular complexes and their spatial organization inside single cells. However, due to the high degree of structural complexity and practical imaging limitations, systematic macromolecular structural recovery inside CECT images remains challenging. Particularly, the recovery of a macromolecule is likely to be biased by its neighbor structures due to the high molecular crowding. To reduce the bias, here we introduce a novel 3D convolutional neural network inspired by Fully Convolutional Network and Encoder-Decoder Architecture for the supervised segmentation of macromolecules of interest in subtomograms. The tests of our models on realistically simulated CECT data demonstrate that our new approach has significantly improved segmentation performance compared to our baseline approach. Also, we demonstrate that the proposed model has generalization ability to segment new structures that do not exist in training data.

Cryo-electron tomography for the structural study of mitochondrial translation

Cryo-electron tomography (cryo-ET) enables the three-dimensional (3D) structural characterization of macromolecular complexes in their physiological environment. Thus, cryo-ET is uniquely suited to study the structural basis of biomolecular processes that are extremely difficult or even impossible to reconstitute using purified components. Translation of mitochondrial genes, which occurs in the secluded interior of mitochondria, falls into this category. Here, we describe the principles of cryo-ET in the context of mitochondrial translation and outline recent developments and challenges of the method. The 3D image of a frozen-hydrated biological sample is computed from its 2D projections, which are acquired using a transmission electron microscope. In conjunction with automated detection of different copies of the molecule of interest and averaging of the corresponding subtomograms, cryo-ET enables macromolecular structure determination in the native environment (i.e. in situ) at sub-nanometer resolution. The preservation of the native environment furthermore allows the extraction of contextual information about the molecules, including the location of specific molecules with respect to membranes, their relative positioning and the spatial organization with respect to other types of macromolecules. Recent preparative developments extend the field of application of cryo-ET from isolated organelles to cultured eukaryotic cells and even tissue, making the traditional borders between molecular and cellular structural biology disappear.

Multi-task Learning for Macromolecule Classification, Segmentation and Coarse Structural Recovery in Cryo-Tomography

Cellular Electron Cryo-Tomography (CECT) is a powerful 3D imaging tool for studying the native structure and organization of macromolecules inside single cells. For systematic recognition and recovery of macromolecular structures captured by CECT, methods for several important tasks such as subtomogram classification and semantic segmentation have been developed. However, the recognition and recovery of macromolecular structures are still very difficult due to high molecular structural diversity, crowding molecular environment, and the imaging limitations of CECT. In this paper, we propose a novel multi-task 3D convolutional neural network model for simultaneous classification, segmentation, and coarse structural recovery of macromolecules of interest in subtomograms. In our model, the learned image features of one task are shared and thereby mutually reinforce the learning of other tasks. Evaluated on realistically simulated and experimental CECT data, our multi-task learning model outperformed all single-task learning methods for classification and segmentation. In addition, we demonstrate that our model can generalize to discover, segment and recover novel structures that do not exist in the training data.

A convolutional autoencoder approach for mining features in cellular electron cryo-tomograms and weakly supervised coarse segmentation

Cellular electron cryo-tomography enables the 3D visualization of cellular organization in the near-native state and at submolecular resolution. However, the contents of cellular tomograms are often complex, making it difficult to automatically isolate different in situ cellular components. In this paper, we propose a convolutional autoencoder-based unsupervised approach to provide a coarse grouping of 3D small subvolumes extracted from tomograms. We demonstrate that the autoencoder can be used for efficient and coarse characterization of features of macromolecular complexes and surfaces, such as membranes. In addition, the autoencoder can be used to detect non-cellular features related to sample preparation and data collection, such as carbon edges from the grid and tomogram boundaries. The autoencoder is also able to detect patterns that may indicate spatial interactions between cellular components. Furthermore, we demonstrate that our autoencoder can be used for weakly supervised semantic segmentation of cellular components, requiring a very small amount of manual annotation.

Deep learning-based subdivision approach for large scale macromolecules structure recovery from electron cryo tomograms

Motivation

Cellular Electron CryoTomography (CECT) enables 3D visualization of cellular organization at near-native state and in sub-molecular resolution, making it a powerful tool for analyzing structures of macromolecular complexes and their spatial organizations inside single cells. However, high degree of structural complexity together with practical imaging limitations makes the systematic de novo discovery of structures within cells challenging. It would likely require averaging and classifying millions of subtomograms potentially containing hundreds of highly heterogeneous structural classes. Although it is no longer difficult to acquire CECT data containing such amount of subtomograms due to advances in data acquisition automation, existing computational approaches have very limited scalability or discrimination ability, making them incapable of processing such amount of data.

Results

To complement existing approaches, in this article we propose a new approach for subdividing subtomograms into smaller but relatively homogeneous subsets. The structures in these subsets can then be separately recovered using existing computation intensive methods. Our approach is based on supervised structural feature extraction using deep learning, in combination with unsupervised clustering and reference-free classification. Our experiments show that, compared with existing unsupervised rotation invariant feature and pose-normalization based approaches, our new approach achieves significant improvements in both discrimination ability and scalability. More importantly, our new approach is able to discover new structural classes and recover structures that do not exist in training data.

Availability and Implementation

Source code freely available at http://www.cs.cmu.edu/∼mxu1/software.

Supplementary information

Supplementary data are available at Bioinformatics online.

Big data in cryoEM: automated collection, processing and accessibility of EM data

The scope and complexity of cryogenic electron microscopy (cryoEM) data has greatly increased, and will continue to do so, due to recent and ongoing technical breakthroughs that have led to much improved resolutions for macromolecular structures solved using this method. This big data explosion includes single particle data as well as tomographic tilt series, both generally acquired as direct detector movies of ∼10-100 frames per image or per tilt-series. We provide a brief survey of the developments leading to the current status, and describe existing cryoEM pipelines, with an emphasis on the scope of data acquisition, methods for automation, and use of cloud storage and computing.